Dynamic Interface-Selection and Resource Allocation Over Heterogeneous Mobile Edge-Computing Wireless Networks With Energy Harvesting
Conference Paper
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
2018 IEEE. Mobile edge computing (MEC) is a promising technique that can significantly enhance the computation capability and save computing energy of mobiles. Despite this, mobile applications may still be interrupted, since mobiles are generally energy-constrained. To overcome this challenge, we propose to integrate energy harvesting (EH) technique into MEC. Based on this notion, we consider the joint optimization of the computation and radio resources together with dynamic interface selection for a heterogeneous MEC system, where a cellular base station (BS), a WiFi access point (AP), and multiple EH mobiles coexist. In the considered scenario, each mobile first harvests energy from radio frequency (RF) signals emitted by the BS, and then utilizes the harvested energy to perform local task execution and partial computation offloading (i.e., offloading part of the computation task to edge clouds). We first formulate the considered resource allocation and interface selection problem as an optimization problem, aiming to maximize all mobiles' total energy saving. Then, we develop an asymptotically optimal scheme and a sub-optimal scheme, through which we can obtain: 1) each mobile's network interface selection between cellular and WiFi; 2) the joint optimization of computation resources, e.g., CPU clock frequencies of edge clouds, and radio resources, e.g., subcarriers; and 3) the optimization of each mobile's energy harvesting time and computation offloading policy. Finally, we evaluate the performance of our proposed schemes through numerical analyses.
